ce-worktree
everyinc/compound-engineering-plugin
Set up isolated git worktrees. Use when starting isolated work, or when ce-work/ce-code-review offers a worktree option; detect existing isolation first.
...Expand allAbout ce-worktree
Worktree Isolation handles the setup of isolated git worktrees so that work can proceed without disturbing the user's main checkout. Because most coding harnesses already create a worktree at session start, the skill's primary job is to detect existing isolation before creating anything redundant. It follows a strict order of operations: detect existing isolation, prefer a native worktree tool, then fall back to plain git only when neither applies.
Detection works by comparing the resolved absolute git directory against the resolved absolute common git directory. Because git mixes absolute and relative path forms depending on the current directory, the skill resolves each to an absolute path first rather than doing a raw string compare, which would otherwise yield a false "already isolated" result. When the two paths differ, it distinguishes a linked worktree from a submodule using the superproject working tree check, and works in place when it is already inside an isolated worktree. When a native worktree primitive exists (such as an EnterWorktree tool, a /worktree command, or a --worktree flag), it uses that and stops, because a behind-the-back git worktree add creates phantom state the harness cannot see or clean up.
The git fallback runs from the repo root, chooses a meaningful branch name derived from the work description, ensures .worktrees/ is gitignored (checking with a trailing slash so directory-only rules are honored), does a best-effort non-fatal fetch of the base branch, creates the worktree under .worktrees/
FAQ
Why does the skill check for existing isolation before creating a worktree?
Most coding harnesses already create a worktree by default at session start, so the common case is that isolation already exists. Creating another worktree from inside one lands in the wrong tree and is invisible to the harness that made the current one.
How does it avoid a false "already isolated" result during detection?
It resolves both the git dir and the common git dir to absolute paths first and compares those, rather than doing a raw string compare. Git returns mixed absolute and relative forms depending on the current directory, which would otherwise produce a false positive.
When should the native worktree tool be used instead of plain git?
Whenever the harness provides a native primitive such as an EnterWorktree/WorktreeCreate tool, a /worktree command, or a --worktree flag, the skill uses it and stops. Native tools place, track, and clean up the worktree so the harness can manage it; a behind-the-back git worktree add creates phantom state the harness cannot see.
What happens if git worktree add fails with a permission or sandbox error?
The failure requires a blocking user decision before touching the current checkout. The skill reports it and asks via the platform's question tool (for example AskUserQuestion in Claude Code), offering options such as working in the current checkout or stopping to resolve the issue, and only continues in the main checkout on explicit confirmation.
How does the skill keep worktree contents from being committed?
Before creating anything it verifies .worktrees/ is gitignored by running git check-ignore with a trailing slash, so an existing directory-only rule is honored even before the directory exists, and adds a .worktrees/ line to .gitignore if needed.
Ensure the current work happens in an isolated workspace, without disturbing the user's main checkout. Most coding harnesses now create a worktree by default at session start, so the common case is that isolation already exists.
Done when: the caller is working in an isolated tree — existing or newly created — and its path and branch have been reported, or a blocker has been reported instead.
Order of operations: detect existing isolation -> prefer a native worktree tool -> fall back to plain git. Never create a worktree the harness cannot see.
Two modes, set by the caller's need:
- New work (default). No ref named — create a fresh branch from a base (trunk). This is what
ce-workandce-code-reviewuse when the user picks the worktree option. - Isolate an existing ref. The caller names a PR head, branch, or commit — attach the worktree to that ref instead of creating a new branch. A branch can be checked out in only one worktree at a time. If the named ref is already checked out anywhere (most commonly as the primary checkout's current branch), do not create a second worktree — report that it is already checked out at
<path>and let the caller act (work there in place; or, only if a clean separate tree is essential, create a detached worktree at the same commit).
Step 0: Detect existing isolation
Compare the resolved absolute git dir against the resolved absolute common git dir. Git mixes absolute and relative forms depending on the current directory (from a subdirectory of a normal checkout, --git-dir comes back absolute while --git-common-dir may be relative), so a raw string compare yields a false "already isolated":
git rev-parse --absolute-git-dir # absolute git dir for this worktree(cd "$(git rev-parse --git-common-dir)" && pwd -P) # absolute shared (common) git dir
Equal -> normal checkout; continue to Step 1.
Different -> a linked worktree or a submodule. Distinguish with git rev-parse --show-superproject-working-tree:
- Non-empty -> submodule; treat it as a normal checkout and continue to Step 1.
- Empty -> already isolated. Report the worktree path (
git rev-parse --show-toplevel) and current branch, then work in place — a worktree-from-worktree lands in the wrong tree and is invisible to the harness that made the current one. In isolate-an-existing-ref mode, check that ref out here (unless it is already current) rather than nesting a worktree.
Step 1: Prefer the harness's native worktree tool
If the harness provides a native worktree primitive — for example an EnterWorktree / WorktreeCreate tool, a /worktree command, or a --worktree flag — use it and stop. Native tools place, track, and clean up the worktree so the harness can manage it. A behind-the-back git worktree add creates phantom state the harness cannot see, navigate to, or clean up.
Step 2: Git fallback
Only when there is no native tool and Step 0 found no existing isolation.
- Run from the repo root:
cd "$(git rev-parse --show-toplevel)". The paths below are repo-root-relative, but the skill runs from the user's current directory — without this,.worktrees/<branch>and the.gitignoreedit land in a subdirectory (e.g.src/.worktrees/...). - Choose a meaningful branch name from the work description (e.g.
feat/login,fix/email-validation) — never an opaque auto-generated one. Base: origin's default branch, elsemain. - Ensure
.worktrees/is gitignored before creating anything:git check-ignore -q .worktrees/— with the trailing slash, so an existing directory-only.worktrees/rule is honored even before the directory exists (without the slash the probe misses it and dirties a correctly-configured repo). Not ignored -> add a.worktrees/line to.gitignore. - Refresh the base with
git fetch origin <from-branch>. This is non-fatal — nooriginremote, a differently-named remote, or a local-only branch is not an abort; continue with the local ref. - Create the worktree, per mode:
- New work:
git worktree add -b <branch-name> .worktrees/<branch-name> origin/<from-branch>(use the local<from-branch>ref iforigin/<from-branch>does not exist). - Existing branch or tag:
git worktree add .worktrees/<slug> <target-ref>. - PR: check it out on a local branch —
git fetch origin pull/<n>/head:pr-<n>thengit worktree add .worktrees/pr-<n> pr-<n>. Never a detachedFETCH_HEAD: that orphans the fix loop's commits instead of updating the PR. (For push-tracking back to the PR, create it detached —git worktree add --detach .worktrees/pr-<n>— thencdin and rungh pr checkout <n>, which is fork-safe.) - If git reports the ref is already checked out elsewhere, apply the one-branch-one-worktree rule above — do not force a second worktree.
- New work:
cdinto it, then report the path and branch.
If git worktree add fails with a sandbox or permission error, the requested isolation does not exist. Do not proceed in the current checkout — the user chose isolation specifically to avoid it. Report the failure and ask, offering options such as "work in the current checkout" vs "stop and resolve the permission issue", using the platform's blocking question tool: AskUserQuestion in Claude Code (call ToolSearch with select:AskUserQuestion first if its schema isn't loaded), request_user_input in Codex, ask_question in Antigravity CLI (agy), ask_user in Pi (via the pi-ask-user extension). Only when no blocking tool exists in the harness or the call errors, present the numbered options in chat and wait for the reply. Never skip the confirmation, and do not retry alternative paths automatically.
All Files
0 filesInstall ce-worktree
Download and extract the skill files to your .claude/skills/ directory.
Download ZIPClone the repository and copy the skill files to your project.
git clone https://github.com/EveryInc/compound-engineering-plugin/blob/main/skills/ce-worktree/SKILL.md # Copy SKILL.md to your .claude/skills/ directory
Copy





Home
